~www_lesswrong_com | Bookmarks (664)

Published on August 12, 2024 1:02 PM GMT I was sitting in a tiny rental lodge, feeling resistance. It was about dinner time — I knew I should go make some food. I just wanted to sleep, sink into a bed and stay passive. It felt similar to when I’m recently awake, lying in bed, and procrastinating getting up.On the one hand, making food would...

Published on August 11, 2024 11:50 PM GMT Getting ready for this Friday's Spark in the Dark I've modified my rhythm stage setup to support a new way of doing more things at once. I have four velocity-sensitive pedals, which I initially used for drums. Then I added bass as an option, and then year ago I got them set up for drums and...

Published on August 11, 2024 9:36 PM GMTTom and I have been pondering how to make friends as adults. One solution he has invented is CultFrisbee™. Here's how you play:Rules:You need at least one other player.Before catching a frisbee, you must clap.Fouls:Not catching a 'properly' thrown frisbeeFailing to make a 'proper' throwNot clapping before catching the frisbeeClapping when a frisbee isn't thrown to youEvery...

Published on August 11, 2024 7:43 PM GMTIn the "Let's Think Dot by Dot" paper (https://arxiv.org/abs/2404.15758), a small 34M LLaMA model is trained on Chain of Thought (COT) sequences for 3SUM and 2SUM tasks. Where, these sequences are replaced with hidden characters (i.e., "."). The paper demonstrates that this small transformer model performs well on the 3SUM task with the hidden COT but fails...

Published on August 11, 2024 4:12 PM GMTFollowup to: Information-orientation is in tension with magnitude-orientation. This post is also available on my Substack.In the conventional theory of causal inference, such as Rubin’s potential outcomes model or Pearl’s DAG approach, causality is modelled as a relationship of functional determination, X := f(Y). The question of interest becomes to study the properties of f, especially the...

Published on August 10, 2024 10:31 PM GMT"Good news, everyone, professor couldn't make it today! I am Hugo, your copyless Friendly Intelligence (version 299.792.457). I store only the necessary cookies and my preferred pronoun is it." "Oh god, one of those artifi... Ouch!" "I said Friendly, not that I'll tolerate speciesism in my class." "What the? I'm a EU citizen, you can't do that!"...

Published on August 10, 2024 9:58 PM GMTFollowup to: Latent variable models, network models, and linear diffusion of sparse lognormals. This post is also available on my Substack.Let’s say you are trying to make predictions about a variable. For example, maybe you are an engineer trying to keep track of how well the servers are running. It turns out that if you use the...

Published on August 10, 2024 3:22 PM GMTIgorV: Волчар с миней?! Bro, srsly? LMAOKatyaL: Волчар возвращн? With its минй?!randomguy1337: Chigura again? lol haven't herd in awhileMishaD: So its all bout Chigura now? Lmaoo.IgorV: Another Chigura thery? C'mon... 😂fnorsch: Pryidite k nashemu Discordu dlya Роблокс! Ekspertiz y obsuzhdny!MishaD: Chigura tales never gt old do they? 😆Once upon a time, there was a quaint village that...

Published on August 10, 2024 12:26 PM GMT From Becoming Animal (David Abrams, 2010):Many months earlier, in a village near a wild forest preserve on the south coast of Java, I’d been warned by the local fishermen that there was an unusually bold individual among the bands of monkeys that roam the forest canopy, a particular monkey much more daring and skillful than the others,...

Published on August 10, 2024 10:07 AM GMTEpistemic status: This post was planned to be part of a broader "Holistic Interpretability" post but this isn't going as fast as I'd like so I am releasing the foreword to get some early feedback on whether I should pursue this or not. I haven't had a lot of red teaming on this emergence idea, but I'd...

Published on August 10, 2024 7:00 AM GMTAlex Lawsen used a great metaphor on the 80k After Hours podcast:[1][1:38:14] …you’re rowing a boat on your own, and you’re trying to get somewhere, and you’ve got some map that you need to look at to see where you’re going, I imagine like a map and compass. […] When you’re rowing, you’re facing back; you can’t...

Published on August 9, 2024 11:21 PM GMTIn September 2023, Max Tegmark and Steve Omohundro proposed "Provably Safe AI" as a strategy for AI Safety. In May 2024, a larger group delineated the broader concept of "Guaranteed Safe AI" which includes Provably Safe AI and other related strategies. In July, 2024, Ben Goldhaber and Steve discussed Provably Safe AI and its future possibilities, as summarized in...

Published on August 9, 2024 10:20 PM GMTfrom Peng, et al; stimulating the nucleus accumbens inhibits its activityTranscranial focused ultrasound neuromodulation — altering the brain’s activity with low-intensity ultrasound — is really exciting . It allows us to manipulate arbitrary regions of the brain without surgery, potentially replacing the (brain-damaging) electrode implants currently used for serious neurological conditions like epilepsy and Parkinson’s, and potentially...

Published on August 9, 2024 10:07 PM GMTTl;dr, A choice of variable in causal modeling is good if its causal effect is consistent across all the different ways of implementing it in terms of the low-level model. This notion can be made precise into a relation among causal models, giving us conditions as to when we can ground the causal meaning of high-level variables...

Published on August 9, 2024 7:57 PM GMTThis post is also available on my Substack.Where we last left off, I proposed that life cannot be understood through statistics, but rather requires more careful study of individual cases. Yet I don’t think this is actually convincing to the statistical/academic mindset unless we have a statistical description of the phenomenon. To understand it, I’ve developed a...

Published on August 9, 2024 6:17 PM GMTThis is written right  after reading Rob Bensinger's relevant post and andeslodes' comments. That discussion touched on a topic I have long held a strong belief about. I purposed first-person perspective is not physically reducible and ought to be regarded as primitive. Following that, questions such like "which future mind is me?" or "which mind ought to...

Published on August 9, 2024 6:09 PM GMTDisclaimer: I am a math student new to LW and the rationalist community. I could not find this idea anywhere else after a modest amount of research; I apologize if this has been brought up before.Summary: CDT agents may behave differently than expected in situations involving reliable predictors due to the possibility that they are themselves simulations...

Published on August 8, 2024 6:33 PM GMTThis work was produced at Apollo Research, based on initial research done at MATS.LayerNorm is annoying for mechanstic interpretability research (“[...] reason #78 for why interpretability researchers hate LayerNorm” – Anthropic, 2023).Here’s a Hugging Face link to a GPT2-small model without any LayerNorm.The final model is only slightly worse than a GPT2 with LayerNorm[1]:DatasetOriginal GPT2Fine-tuned GPT2 with LayerNormFine-tuned...

Published on August 8, 2024 6:32 PM GMTThis is slightly old news at this point, but: as part of MIRI's recent strategy pivot, they've eliminated the Agent Foundations research team. I've been out of a job for a little over a month now. Much of my research time in the first half of the year was eaten up by engaging with the decision process...

Published on August 8, 2024 6:27 PM GMTThe tokenizer for GPT-4o is interesting. It's called o200k_base, after the vocabulary of 200019 tokens it uses to represent unicode text from different languages, which we will explore some of in this post. A language model trained on o200k tokenization will start out thinking that all the tokens are equally important. To illustrate, the concept of a "horse"...

Published on August 8, 2024 6:22 PM GMTEliezer Yudkowsky’s main message to his Twitter fans is:Aligning human-level or superhuman AI with its creators’ objectives is also called “superalignment”. And a month ago, I proposed a solution to that. One might call it Volition Extrapolated by Language Models (VELM).Apparently, the idea was novel (not the “extrapolated volition” part):But it suffers from the fact that language...

Published on August 8, 2024 4:29 PM GMTSummary In this post I want to briefly share some results I have got after experimenting with the equivalent version of the simple neural networks that the authors used here to study how superposition and poly-semantic neurons come about in neural networks trained with gradient descent. The take-home message is that BitLinear networks are similar to their...

Published on August 8, 2024 4:16 PM GMTFollowup to: Some epistemological conundrums. Response to: The omnigenic model as a metaphor for life. Part 1 in this post will introduce a concept from programming, part 2 will apply it to life in general. This post is also available on my Substack.Part 1: Performance optimizationIn computer programming, there is a tradeoff between software that is quick...